© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161629
    Prev
    Next
    INDEX
    Explanations

    sports and finance terminology

    np_acts-logits-general · gemini-2.5-flash-lite

    MA model or serve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    et
    0.52
     Calvin
    0.49
    ann
    0.47
    CHI
    0.46
    iel
    0.46
    .
    0.45
    etter
    0.45
    MO
    0.45
    intr
    0.45
    خم
    0.44
    POSITIVE LOGITS
     dificuldade
    0.52
     estação
    0.52
     उत्पाद
    0.51
     excluir
    0.50
     güçlü
    0.49
     difficoltà
    0.48
     ভালোভাবে
    0.46
    Ꮓ
    0.46
     সৃষ্টির
    0.46
    ংখ্যান
    0.46
    Activations Density 0.001%

    No Known Activations